Ondřej Přibyl

Clustering of Activity Patterns Using Genetic Algorithms

Finding groups of individuals with similar activity patterns (a sequence of activities within a given time period, usually 24 hours) has become an important issue in models of activity-based approaches to travel demand analysis. This knowledge is critical to many activity-based models, and it aids our understanding of activity/travel behavior. This paper aims to develop a methodology for the clustering of these patterns. There is a large number of well-known clustering algorithms, such as hierarchical clustering, or k-means clustering (which belongs to the class of partitioning algorithm). However, these algorithms cannot be used to cluster categorical data, so they do not suit the problem of clustering of activity patterns well. Several other heuristics have been developed to overcome this problem. The k-medoids algorithm, described in this paper, is a modification of the k-means algorithm with respect to categorical data. However, similar to the k-means algorithm, the k-medoids algorithm can converge to local optima. This paper approaches the medoids-based formulation of clustering problem using genetic algorithms (GAs), a probabilistic search algorithm that simulates natural evolution. The main objective of this paper is to develop a robust algorithm that suits the problem of clustering of activity patterns and to demonstrate and discuss its properties.

Application of Adaptive Neuro-Fuzzy Inference System to Analysis of Travel Behavior

A relatively new method for data analysis called the adaptive neuro-fuzzy inference system (ANFIS) is illustrated with an example from travel behavior modeling. The options offered by this data analysis technique are illustrated by using data from Australia. In addition, an experiment was performed to identify the optimal split of data into an estimation sample and a validation sample. Comparisons of ANFIS and the more traditional regression methods such as ordinary least-squares linear regression and negative binomial regression were performed by using the mean square error and correlation coefficients. ANFIS is shown to be a useful tool, and its further use in travel behavior research and applications in transportation planning is recommended. However, many additional issues require further scrutiny and experimentation, which are discussed.

CROSS-STUDY RESEARCH ON UTILITY AND VALIDITY OF DRIVING SIMULATOR FOR DRIVER BEHAVIOR ANALYSIS

Driving is one of the most ordinary and universal everyday tasks and, at the same time, one of the most complex and dangerous. It requires a full range of sensory, perceptual, cognitive, and motor functions, all of which can be affected by a wide range of stressors and experience levels. Therefore, exploring of human behaviour while controlling a vehicle is a crucial task in improving traffic safety. Experimental studies can always be conducted with on-road tests, however, using a simulator is safer and more cost-effective. The main goal of this paper is to demonstrate if and under what conditions could a driving simulator provide sufficient results required for a proper study of driver behavior. It discusses its limits and advantages. Overall, the research reviewed in this paper indicates that simulator driving behaviour approximates (relative validity of speed and lateral position of vehicle on road), but does not exactly replicate (absolute validity), on-road driving behaviour.

Effective Decision Support System Based on Statistical Tools

This paper focuses on an important topic – on evaluation of various transport structures. It is a typical situation that a decision maker must choose from various alternatives and with respect to different, often contradicting criteria. In this paper, a method adopted from the field of risk management, SAFMEA, was adopted. This is a novel approach that however introduces statistical evaluation of expert feedback to provide a robust decision support materials. Here, in a structured way, the expert know how is extracted and processed. In this approach, not only average aggregate values are evaluated. An important contribution of this approach is in looking into the variances in the answers from particular experts in order to capture the consensus or the lack of it. The method was validated on a case study from the Czech Republic, particularly on evaluating four different approaches to modernization of a highway D1. The method provided a recommendation that has been as a result actually implemented by the ministry of transport. The results confirm that the approach is worth consideration.

Mobile Highway Telematics System on D1 Highway in the Czech Republic

Highway management systems belong to modern methods enhancing capacity and increasing safety on highways, while using strategies such as variable speed limits, ramp metering, information about alternative routes or danger on road and others. Typically, they use static infrastructure, i.e. fixed sensors and gantries with variable message signs, which are not very effective in case of constructions.

Fuzzy Algorithm for Highway Speed Harmonisation in VISSIM

In this paper is demonstrated, how a fuzzy control system can be implemented and verified directly in a microsimulation tool from the company PTV, VISSIM. A new fuzzy algorithm for speed harmonisation is developed and its implementation is explained in details. The main advantage of this solution is in the direct implementation of the control algorithm in the microsimulation tool without the need to deal with an API and external software. Additionally, the configuration and optimisation of the control algorithm is performed quickly in the tool and directly responds to the microsimulation results. This has an impact on the time to implement such a solution as well as the overall cost, since a single resource able to work with the microsimulation tool can do the work and no programming experience are required.